Update README.md

Low RAM code updated

README.md

@@ -147,6 +147,22 @@ inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7, top_p=0.9)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
+
+##### if you on LOW RAM or CPU
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "techpro-saida/msci_software_engineering_slm_v1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu")
+
+prompt = "Explain SOLID principles in OOP?"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=60, temperature=0.7)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+
 ```
 
 ## Developer